Deep Parallel MRI Reconstruction Network Without Coil Sensitivities

Bian, Wanyu; Chen, Yunmei; Ye, Xiaojing

doi:10.1007/978-3-030-61598-7_2

Cited by 9 publications

(10 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The parameters of the network in each phase are not shared. All the substitutions have been mathematically proven to be effective 28,36 . Then step () becomes

\begin{align} δ_{i}^{false(t false)} & = 𝒢_{{normalΘ}_{i}}^{false(t false)} false({\overset{δ}{true}}_{i}^{false(t false)} false) + {\overset{δ}{true}}_{i}^{false(t false)}, \end{align}

\begin{align} = {\overset{𝒟}{true}}_{{normalΘ}_{i}}^{false(t false)} \circ 𝒮_{β_{i}^{false(t false)}} \circ 𝒟_{{normalΘ}_{i}}^{false(t false)} false({\overset{δ}{true}}_{i}^{false(t false)} false) + {\overset{δ}{true}}_{i}^{false(t false)}, \forall i = 1, \dots, N, \end{align}

…”

Section: Methodsmentioning

confidence: 99%

Improving quantitative MRI using self‐supervised deep learning with model reinforcement: Demonstration for rapid T1 mapping

Bian,

Jang,

Liu

2024

Magnetic Resonance in Med

Self Cite

View full text Add to dashboard Cite

PurposeThis paper proposes a novel self‐supervised learning framework that uses model reinforcement, REference‐free LAtent map eXtraction with MOdel REinforcement (RELAX‐MORE), for accelerated quantitative MRI (qMRI) reconstruction. The proposed method uses an optimization algorithm to unroll an iterative model‐based qMRI reconstruction into a deep learning framework, enabling accelerated MR parameter maps that are highly accurate and robust.MethodsUnlike conventional deep learning methods which require large amounts of training data, RELAX‐MORE is a subject‐specific method that can be trained on single‐subject data through self‐supervised learning, making it accessible and practically applicable to many qMRI studies. Using quantitative mapping as an example, the proposed method was applied to the brain, knee and phantom data.ResultsThe proposed method generates high‐quality MR parameter maps that correct for image artifacts, removes noise, and recovers image features in regions of imperfect image conditions. Compared with other state‐of‐the‐art conventional and deep learning methods, RELAX‐MORE significantly improves efficiency, accuracy, robustness, and generalizability for rapid MR parameter mapping.ConclusionThis work demonstrates the feasibility of a new self‐supervised learning method for rapid MR parameter mapping, that is readily adaptable to the clinical translation of qMRI.

show abstract

“…The parameters of the network in each phase are not shared. All the substitutions have been mathematically proven to be effective 28,36 . Then step () becomes

\begin{align} δ_{i}^{false(t false)} & = 𝒢_{{normalΘ}_{i}}^{false(t false)} false({\overset{δ}{true}}_{i}^{false(t false)} false) + {\overset{δ}{true}}_{i}^{false(t false)}, \end{align}

\begin{align} = {\overset{𝒟}{true}}_{{normalΘ}_{i}}^{false(t false)} \circ 𝒮_{β_{i}^{false(t false)}} \circ 𝒟_{{normalΘ}_{i}}^{false(t false)} false({\overset{δ}{true}}_{i}^{false(t false)} false) + {\overset{δ}{true}}_{i}^{false(t false)}, \forall i = 1, \dots, N, \end{align}

…”

Section: Methodsmentioning

confidence: 99%

Improving quantitative MRI using self‐supervised deep learning with model reinforcement: Demonstration for rapid T1 mapping

Bian,

Jang,

Liu

2024

Magnetic Resonance in Med

Self Cite

View full text Add to dashboard Cite

show abstract

“…Complex Highly-constrained back-projection (HYPR) local reconstruction (LR) [56] technique and the expectation maximization algorithm based method [12] have been proposed to solve for complex-valued image reconstruction problem. Most existing deep-learning based MRI reconstruction apply standard real-valued convolutions and nonlinear activation functions to the real and imaginary parts separately [5,21,3,62]. Cole .…”

Section: Related Workmentioning

confidence: 99%

“…The present work is a substantial extension of the preliminary work in [5] using domain-hybrid network with a trained initialization to solve for an optimal control pMRI joint-channel reconstruction problem when coil-sensitivity is unavailable. More comprehensive empirical study is conducted in this work.…”

Section: Related Workmentioning

confidence: 99%

“… represents soft shrinkage operator, we set 0 = 0 for both real and imaginary parts. Details for this model was explained in the conference paper [5]. The proximal operator is learned in residual update (25b) and only performs in the image domain.…”

Section: Ablation Studiesmentioning

confidence: 99%

“…Figure6: The framework paradigm for all phases with three different initial reconstruction methods, including zero-filled initial, SPIRiT reconstruction initial, and the learned initial. For = 1, ⋯ , , each phase follows the algorithm introduced in our previous work[5].…”

mentioning

confidence: 99%

See 2 more Smart Citations

An Optimal Control Framework for Joint-channel Parallel MRI Reconstruction without Coil Sensitivities

Bian¹,

Chen²,

Ye³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

This work aims at developing a novel calibration-free fast parallel MRI (pMRI) reconstruction method incorporate with discrete-time optimal control framework. The reconstruction model is designed to learn a regularization that combines channels and extracts features by leveraging the information sharing among channels of multi-coil images. We propose to recover both magnitude and phase information by taking advantage of structured multiplayer convolutional networks in image and Fourier spaces. Methods: We develop a novel variational model with a learnable objective function that integrates an adaptive multi-coil image combination operator and effective image regularization in the image and Fourier spaces. We cast the reconstruction network as a structured discrete-time optimal control system, resulting in an optimal control formulation of parameter training where the parameters of the objective function play the role of control variables. We demonstrate that the Lagrangian method for solving the control problem is equivalent to back-propagation, ensuring the local convergence of the training algorithm. Results: We conduct a large number of numerical experiments of the proposed method with comparisons to several state-of-the-art pMRI reconstruction networks on real pMRI datasets. The numerical results demonstrate the promising performance of the proposed method evidently. Conclusion: The proposed method provides a general deep network design and training framework for efficient joint-channel pMRI reconstruction. Significance: By learning multi-coil image combination operator and performing regularizations in both image domain and k-space domain, the proposed method achieves a highly efficient image reconstruction network for pMRI.

show abstract

Preoperative Radiomics Approach to Evaluating Tumor‐Infiltrating CD8⁺ T Cells in Patients With Pancreatic Ductal Adenocarcinoma Using Noncontrast Magnetic Resonance Imaging

Bian

Liu

et al. 2021

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Background: CD8 + T cell in pancreatic ductal adenocarcinoma (PDAC) is closely related to the prognosis and treatment response of patients. Accurate preoperative CD8 + T-cell expression can better identify the population benefitting from immunotherapy. Purpose: To develop and validate a machine learning classifier based on noncontrast magnetic resonance imaging (MRI) for the preoperative prediction of CD8 + T-cell expression in patients with PDAC. Study Type: Retrospective cohort study. Population: Overall, 114 patients with PDAC undergoing MR scan and surgical resection; 97 and 47 patients in the training and validation cohorts. Field Strength/Sequence/3 T: Breath-hold single-shot fast-spin echo T2-weighted sequence and noncontrast T1-weighted fat-suppressed sequences. Assessment: CD8 + T-cell expression was quantified using immunohistochemistry. For each patient, 2232 radiomics features were extracted from noncontrast T1-and T2-weighted images and reduced using the Wilcoxon rank-sum test and least absolute shrinkage and selection operator method. Linear discriminative analysis was used to construct radiomics and mixed models. Model performance was determined by its discriminative ability, calibration, and clinical utility. Statistical Tests: Kaplan-Meier estimates, Student's t-test, the Kruskal-Wallis H test, and the chi-square test, receiver operating characteristic curve, and decision curve analysis. Results: A log-rank test showed that the survival duration in the CD8-high group (25.51 months) was significantly longer than that in the CD8-low group (22.92 months). The mixed model included all MRI characteristics and 13 selected radiomics features, and the area under the curve (AUC) was 0.89 (95% confidence interval [CI], 0.77-0.92) and 0.69 (95% CI, 0.53-0.82) in the training and validation cohorts. The radiomics model included 13 radiomics features, which showed good discrimination in the training cohort (AUC, 0.85; 95% CI, 0.77-0.92) and the validation cohort (AUC, 0.76; 95% CI, 0.61-0.87). Data Conclusions: This study developed a noncontrast MRI-based radiomics model that can preoperatively determine CD8 + T-cell expression in patients with PDAC and potentially immunotherapy planning.

show abstract

Deep Parallel MRI Reconstruction Network Without Coil Sensitivities

Cited by 9 publications

References 23 publications

Improving quantitative MRI using self‐supervised deep learning with model reinforcement: Demonstration for rapid T1 mapping

Improving quantitative MRI using self‐supervised deep learning with model reinforcement: Demonstration for rapid T1 mapping

An Optimal Control Framework for Joint-channel Parallel MRI Reconstruction without Coil Sensitivities

Preoperative Radiomics Approach to Evaluating Tumor‐Infiltrating CD8⁺ T Cells in Patients With Pancreatic Ductal Adenocarcinoma Using Noncontrast Magnetic Resonance Imaging

Contact Info

Product

Resources

About

Deep Parallel MRI Reconstruction Network Without Coil Sensitivities

Cited by 9 publications

References 23 publications

Improving quantitative MRI using self‐supervised deep learning with model reinforcement: Demonstration for rapid T1 mapping

Improving quantitative MRI using self‐supervised deep learning with model reinforcement: Demonstration for rapid T1 mapping

An Optimal Control Framework for Joint-channel Parallel MRI Reconstruction without Coil Sensitivities

Preoperative Radiomics Approach to Evaluating Tumor‐Infiltrating CD8+ T Cells in Patients With Pancreatic Ductal Adenocarcinoma Using Noncontrast Magnetic Resonance Imaging

Contact Info

Product

Resources

About

Preoperative Radiomics Approach to Evaluating Tumor‐Infiltrating CD8⁺ T Cells in Patients With Pancreatic Ductal Adenocarcinoma Using Noncontrast Magnetic Resonance Imaging